NVIDIA · nemotron family
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Provider-specific prices and limits stay separate from canonical model facts.
| Provider | Provider model ID | Input | Output | Context | Output limit |
|---|---|---|---|---|---|
| Nvidia | nvidia/nemotron-3-ultra-550b-a55b | $0.5 / 1M | $2.5 / 1M | 1,000,000 | 65,536 |
| OpenRouter | nvidia/nemotron-3-ultra-550b-a55b | $0.6 / 1M | $3.6 / 1M | 1,000,000 | 16,384 |
| Together AI | nvidia/nemotron-3-ultra-550b-a55b | $0.6 / 1M | $3.6 / 1M | 512,300 | 512,300 |
Attachments
No
Reasoning
Yes
Tool calling
Yes
Structured output
Unknown
Temperature
Yes
| Vercel AI Gateway | nvidia/nemotron-3-ultra-550b-a55b | $0.6 / 1M | $2.4 / 1M | 1,000,000 | 65,000 |